From 2779babcab17cf02377f69a7f417f4487332bd3f Mon Sep 17 00:00:00 2001
From: Richard Loyer <richard.loyer@c42.lu>
Date: Sun, 24 May 2026 13:01:16 +0200
Subject: [PATCH] Rebuild upstream+hexagon: configure OK (NDK r27d, SDK 6.5,
 v79), build lance

---
 CLAUDE.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/CLAUDE.md b/CLAUDE.md
index e90c80e..172b964 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -35,6 +35,8 @@ Pas l'intégration minimale. Cible: Qwen3.5-4B near-ExecuTorch sur Pad3, mémoir
 2. **Bencher `qwen35_compile` HTP existant**: 0%, partiel ou OK? décide écrire-vs-finir kernel.
 3. Baseline prefill GDN CPU à battre. Mémoire <4 GB Q4_0/Q6_K-embeds. Itérer kernel si gap.
 
+Source: `/opt/Kazeia/to_delete/llama.cpp` = upstream ggerganov + ggml-hexagon + htp + qwen35_compile, commit f0fe1058b. Backend Hexagon prod: libggml-hexagon (CPU) + libggml-htp-v79 (auto). Session HTP plafond 3.5GB → NDEV multi-device si >. NDK r27d, Hexagon SDK 6.5.0.0. Rebuild en cours.
+
 ## Limite assistant
 R&D LLM frontière (kernels HVX bit-exacts, quant) = aide partielle, je le dis au cas par cas.
 GGUF/llama.cpp archivés vers `/opt/Kazeia/to_delete`. Git local: commits réguliers. — Richard & Damien.